{ "openapi": "3.0.1", "info": { "title": "Website Change Monitor — Sitemap & Page Content Diff", "description": "Track website changes via sitemaps: finds new, removed and updated pages (lastmod) and detects page content changes with normalized hashes and word-level diff previews. Pay per page checked ($0.0005) and per change detected ($0.002).", "version": "0.1", "x-build-id": "wuKt3rZErkek3qq1U" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/owlabee~website-change-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-owlabee-website-change-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/owlabee~website-change-monitor/runs": { "post": { "operationId": "runs-sync-owlabee-website-change-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/owlabee~website-change-monitor/run-sync": { "post": { "operationId": "run-sync-owlabee-website-change-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "sites" ], "properties": { "sites": { "title": "Sites or sitemap URLs", "minItems": 1, "type": "array", "description": "One entry per line. A site URL (https://example.com) is resolved through robots.txt `Sitemap:` lines, then /sitemap.xml and /sitemap_index.xml. A direct sitemap URL (.xml, .xml.gz, .txt, sitemap indexes) is used as-is. The prefilled value is the cheap, always-available example used by Apify's daily automated test.", "items": { "type": "string" } }, "mode": { "title": "Mode", "enum": [ "discover", "monitor" ], "type": "string", "description": "`discover` lists every page URL found in the sitemaps with lastmod/changefreq/priority (no page fetches, no state). `monitor` compares this run with the previous snapshot and emits change records; the first monitor run writes baseline records.", "default": "monitor" }, "checkContent": { "title": "Check page content", "type": "boolean", "description": "Monitor mode only. Fetch each HTML page (max 1 MB, 20 s timeout), normalize its text and hash it, so `content-changed` and `status-changed` records are produced in addition to sitemap-level changes. Turn off to compare sitemap data only (much faster, no page requests).", "default": true }, "contentSelector": { "title": "Content CSS selector", "type": "string", "description": "Comma-separated CSS selectors; the first one that matches a non-empty element is hashed. Default `main, article, body`. Use it to ignore headers, footers and sidebars, e.g. `#content, .post-body`." }, "ignoreNumbers": { "title": "Ignore numbers and dates", "type": "boolean", "description": "Strip digits, dates and times before hashing so view counters, timestamps and prices do not count as content changes.", "default": false }, "maxPages": { "title": "Max pages per site", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Upper bound on page URLs taken from the sitemaps of each site (after include/exclude filtering, in sitemap order). In monitor mode set it above the site's real page count so removals are detected correctly.", "default": 500 }, "includePatterns": { "title": "Include URL patterns", "type": "array", "description": "Only keep page URLs matching at least one pattern. Globs (`https://example.com/blog/*`), regular expressions (`/\\/docs\\/v\\d+\\//`) or plain substrings (`/pricing`). Empty = keep all.", "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Drop page URLs matching any pattern (same syntax as include patterns), e.g. `*/tag/*`, `/\\.pdf$/`.", "items": { "type": "string" } }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Parallel page fetches. Requests to the same host are additionally spaced at least 500 ms apart to stay polite (about 2 requests per second per host).", "default": 5 }, "stateStoreName": { "title": "State key-value store", "pattern": "^[a-zA-Z0-9-]{3,63}$", "type": "string", "description": "Named key-value store that keeps one snapshot per site between monitor runs. Use a different name to keep independent baselines (e.g. per client or per schedule).", "default": "website-change-monitor-state" }, "resetBaseline": { "title": "Reset baseline", "type": "boolean", "description": "Ignore the stored snapshot and write a fresh baseline for every site in this run.", "default": false }, "webhookUrl": { "title": "Webhook URL (optional)", "pattern": "^https?://.+", "type": "string", "description": "If set, the Actor POSTs a JSON summary of the run and the list of change records to this URL (10 s timeout, 2 retries). Failures are logged, never fatal." }, "notifyOnlyOnChanges": { "title": "Notify only on changes", "type": "boolean", "description": "Monitor mode: call the webhook only when at least one change record was produced. Turn off to receive a webhook after every run.", "default": true } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }